GMI Cloud models & pricing

GMI Cloud hosts 17 models (17 with public pricing) covering 1 modalities. Asia-Pacific GPU cloud with serverless inference for Llama and Qwen. Cheapest input starts at $0.150/M tokens; the most premium goes up to $15.00/M. Use Future AGI's Agent Command Center to route any GMI Cloud model with cost-optimized fallback and unified observability.

Homepage ↗ Docs ↗

chat 17

Model Input / 1M Output / 1M Context Caps
OpenAI GPT 4o mini $0.150/M $0.600/M 131,072 tools · vision
DeepSeek AI DeepSeek v3.0324 $0.280/M $0.880/M 163,840 tools
DeepSeek AI DeepSeek v3.2 $0.280/M $0.400/M 163,840 tools
Minimaxai Minimax M2.1 $0.300/M $1.20/M 196,608
Qwen Qwen3 VL 235B A22b Instruct Fp8 $0.300/M $1.40/M 262,144 vision
Zai Org Glm 4.7 Fp8 $0.400/M $2.00/M 202,752
Google Gemini 3 Flash preview $0.500/M $3.00/M 1,048,576 tools · vision
Moonshotai Kimi K2 Thinking $0.800/M $1.20/M 262,144
OpenAI GPT 5 $1.25/M $10.00/M 409,600 tools
OpenAI GPT 5.1 $1.25/M $10.00/M 409,600 tools
OpenAI GPT 5.2 $1.75/M $14.00/M 409,600 tools
Google Gemini 3 Pro preview $2.00/M $12.00/M 1,048,576 tools · vision
OpenAI GPT 4o $2.50/M $10.00/M 131,072 tools · vision
Anthropic Claude Sonnet 4 $3.00/M $15.00/M 409,600 tools · vision
Anthropic Claude Sonnet 4.5 $3.00/M $15.00/M 409,600 tools · vision
Anthropic Claude Opus 4.5 $5.00/M $25.00/M 409,600 tools · vision
Anthropic Claude Opus 4 $15.00/M $75.00/M 409,600 tools · vision

FAQ

How many GMI Cloud models are there?

17 GMI Cloud models are listed across 1 modality on this page. 17 have public per-token pricing.

How is GMI Cloud pricing verified?

Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.

Which GMI Cloud model is cheapest?

Input pricing on GMI Cloud starts at $0.150 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.

Can I route to GMI Cloud via an OpenAI-compatible API?

Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a GMI Cloud target, and call GMI Cloud models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.

Route any GMI Cloud model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.